The primary driving force behind the emergence of artificial intelligence in medical imaging is to increase clinical efficiency. As radiological imaging data continuously increases, the limited number of experts available to evaluate this data makes interpretation and reporting processes increasingly challenging. Such evaluations are often based on training and experience and can sometimes be subjective. While these qualitative evaluations are superior, AI excels at recognizing complex patterns in imaging data and can provide an automated quantitative assessment. When integrated into clinical workflows as a tool to assist experts performing and interpreting radiological examinations, AI can enable more accurate and reproducible radiology assessments. Research in many medical fields has greatly benefited from these approaches, enabling the development of faster and more reproducible quantitative imaging markers. These markers have been used to aid in disease diagnosis, prognosis determination, patient selection for treatment, and monitoring response to treatment. With these types of artificial intelligence programs, the automated segmentation of organs and tissues throughout the body in computed tomography and magnetic resonance imaging has been enhanced. The aim of this section is to demonstrate how artificial intelligence applications significantly contribute to improving image quality, reducing artifacts, automating lesion detection and classification, and increasing diagnostic accuracy in different modalities such as radiography, oral radiology, mammography, ultrasonography, computed tomography, and magnetic resonance imaging. Deep learning-based algorithms optimize clinical workflows and the application of radiological examinations, while strengthening radiologists' decision support processes and enabling the development of faster, more reliable, and standardized approaches in patient management.